Commit c93c6223 ("xprtrdma: Disconnect on registration failure")
added a disconnect for some RPC marshaling failures. This is needed
only in a handful of cases, but it was triggering for simple stuff
like temporary resource shortages. Try to straighten this out.

Fix up the lower layers so they don't return -ENOMEM or other error
codes that the RPC client's FSM doesn't explicitly recognize.

Also fix up the places in the send_request path that do want a
disconnect. For example, when ib_post_send or ib_post_recv fail,
this is a sign that there is a send or receive queue resource
miscalculation. That should be rare, and is a sign of a software
bug. But xprtrdma can recover: disconnect to reset the transport and
start over.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Not having an rpcrdma_rep at call_allocate time can be a problem.
It means that send_request can't post a receive buffer to catch
the RPC's reply. Possible consequences are RPC timeouts or even
transport deadlock.

Instead of allowing an RPC to proceed if an rpcrdma_rep is
not available, return NULL to force call_allocate to wait and
try again.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Clean up: Move device capability detection into memreg-specific
source files.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Clean up: ALLPHYSICAL is gone and FMR has been converted to use
scatterlists. There are no more users of these functions.

This patch shrinks the size of struct rpcrdma_req by about 3500
bytes on x86_64. There is one of these structs for each RPC credit
(128 credits per transport connection).
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

No HCA or RNIC in the kernel tree requires the use of ALLPHYSICAL.

ALLPHYSICAL advertises in the clear on the network fabric an R_key
that is good for all of the client's memory. No known exploit
exists, but theoretically any user on the server can use that R_key
on the client's QP to read or update any part of the client's memory.

ALLPHYSICAL exposes the client to server bugs, including:
 o base/bounds errors causing data outside the i/o buffer to be
   accessed
 o RDMA access after reply causing data corruption and/or integrity
   fail

ALLPHYSICAL can't protect application memory regions from server
update after a local signal or soft timeout has terminated an RPC.

ALLPHYSICAL chunks are no larger than a page. Special cases to
handle small chunks and long chunk lists have been a source of
implementation complexity and bugs.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Based on code audit.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

I found that commit ead3f26e ("xprtrdma: Add ro_unmap_safe
memreg method"), which introduces ro_unmap_safe, never wired up the
FMR recovery worker.

The FMR and FRWR recovery work queues both do the same thing.
Instead of setting up separate individual work queues for this,
schedule a delayed worker to deal with them, since recovering MRs is
not performance-critical.

Fixes: ead3f26e ("xprtrdma: Add ro_unmap_safe memreg method")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

The use of a scatterlist for handling DMA mapping and unmapping
was recently introduced in frwr_ops.c in commit 4143f34e
("xprtrdma: Port to new memory registration API"). That commit did
not make a similar update to xprtrdma's FMR support because the
core ib_map_phys_fmr() and ib_unmap_fmr() APIs have not been changed
to take a scatterlist argument.

However, FMR still needs to do DMA mapping and unmapping. It appears
that RDS, for example, uses a scatterlist for this, then builds the
DMA addr array for the ib_map_phys_fmr call separately. I see that
SRP also utilizes a scatterlist for DMA mapping. xprtrdma can do
something similar.

This modernization is used immediately to properly defer DMA
unmapping during fmr_unmap_safe (a FIXME). It separates the DMA
unmapping coordinates from the rl_segments array. This array, being
part of an rpcrdma_req, is always re-used immediately when an RPC
exits. A scatterlist is allocated in memory independent of the
rl_segments array, so it can be preserved indefinitely (ie, until
the MR invalidation and DMA unmapping can actually be done by a
worker thread).

The FRWR and FMR DMA mapping code are slightly different from each
other now, and will diverge further when the "Check for holes" logic
can be removed from FRWR (support for SG_GAP MRs). So I chose not to
create helpers for the common-looking code.

Fixes: ead3f26e ("xprtrdma: Add ro_unmap_safe memreg method")
Suggested-by: Sagi Grimberg <sagi@lightbits.io>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Clean up: Use the same naming convention used in other
RPC/RDMA-related data structures.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Clean up: Moving these helpers in a separate patch makes later
patches more readable.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Clean up: FMR is about to replace the rpcrdma_map_one code with
scatterlists. Move the scatterlist fields out of the FRWR-specific
union and into the generic part of rpcrdma_mw.

One minor change: -EIO is now returned if FRWR registration fails.
The RPC is terminated immediately, since the problem is likely due
to a software bug, thus retrying likely won't help.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

ib_unmap_fmr() takes a list of FMRs to unmap. However, it does not
remove the FMRs from this list as it processes them. Other
ib_unmap_fmr() call sites are careful to remove FMRs from the list
after ib_unmap_fmr() returns.

Since commit 7c7a5390 ("xprtrdma: Add ro_unmap_sync method for FMR")
fmr_op_unmap_sync passes more than one FMR to ib_unmap_fmr(), but
it didn't bother to remove the FMRs from that list once the call was
complete.

I've noticed some instability that could be related to list
tangling by the new fmr_op_unmap_sync() logic. In an abundance
of caution, add some defensive logic to clean up properly after
ib_unmap_fmr().

Fixes: 7c7a5390 ("xprtrdma: Add ro_unmap_sync method for FMR")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

The well-spotted fallocate undo fix is good in most cases, but not when
fallocate failed on the very first page.  index 0 then passes lend -1
to shmem_undo_range(), and that has two bad effects: (a) that it will
undo every fallocation throughout the file, unrestricted by the current
range; but more importantly (b) it can cause the undo to hang, because
lend -1 is treated as truncation, which makes it keep on retrying until
every page has gone, but those already fully instantiated will never go
away.  Big thank you to xfstests generic/269 which demonstrates this.

Fixes: b9b4bb26 ("tmpfs: don't undo fallocate past its last page")
Cc: stable@vger.kernel.org
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Pull MIPS fix from Ralf Baechle:
 "Another week with just a single 4.7 fix.

  This fixes a possible 'loss' of the huge page bit from pmd on
  permission change"

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus:
  MIPS: Fix page table corruption on THP permission changes.

Pull SCSI fixes from James Bottomley:
 "Three fixes.  One is the qla24xx MSI regression, one is a theoretical
  problem over blacklist matching, which would bite USB badly if it ever
  triggered and one is a system hang with a particular type of IPR
  device"

* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
  qla2xxx: Fix NULL pointer deref in QLA interrupt
  SCSI: fix new bug in scsi_dev_info_list string matching
  ipr: Clear interrupt on croc/crocodile when running with LSI

Merge tag 'ecryptfs-4.7-rc7-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs

Pull eCryptfs fixes from Tyler Hicks:
 "Provide a more concise fix for CVE-2016-1583:
   - Additionally fixes linux-stable regressions caused by the
     cherry-picking of the original fix

  Some very minor changes that have queued up:
   - Fix typos in code comments
   - Remove unnecessary check for NULL before destroying kmem_cache"

* tag 'ecryptfs-4.7-rc7-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs:
  ecryptfs: don't allow mmap when the lower fs doesn't support it
  Revert "ecryptfs: forbid opening files without mmap handler"
  ecryptfs: fix spelling mistakes
  eCryptfs: fix typos in comment
  ecryptfs: drop null test before destroy functions

Pull IOMMU fixes from Joerg Roedel:
 "Two Fixes:

   - Intel VT-d fix for a suspend/resume issue, introduced with the
     scalability improvements in this cycle.

   - AMD IOMMU fix for systems that have unity mappings defined.  There
     was a race where translation got enabled before the unity mappings
     were in place.  This issue was seen on some HP servers"

* tag 'iommu-fixes-v4.7-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/amd: Fix unity mapping initialization race
  iommu/vt-d: Fix infinite loop in free_all_cpu_cached_iovas

Pull xen bug fixes from David Vrabel:

 - Fix two bugs in the handling of xenbus transactions.

 - Make the xen acpi driver compatible with Xen 4.7.

* tag 'for-linus-4.7b-rc6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/acpi: allow xen-acpi-processor driver to load on Xen 4.7
  xenbus: simplify xenbus_dev_request_and_reply()
  xenbus: don't bail early from xenbus_dev_request_and_reply()
  xenbus: don't BUG() on user mode induced condition

Pull arm64 fixes from Will Deacon:
 "A couple of late fixes here, but one that we've been sitting on for a
  few weeks while the details were worked out.  Specifically, we now
  enforce USER_DS on taking exceptions whilst in the kernel, which
  avoids leaking kernel data to userspace through things like perf.  The
  other patch is an update to a workaround for a hardware erratum on
  some Cavium SoCs.

  Summary:

   - Enforce USER_DS on exception entry from EL1

   - Apply workaround for Cavium errata #27456 on Thunderx-81xx parts"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: Enable workaround for Cavium erratum 27456 on thunderx-81xx
  arm64: kernel: Save and restore UAO and addr_limit on exception entry

Pull x86 fixes from Ingo Molnar:
 "Three fixes:

   - A boot crash fix with certain configs
   - a MAINTAINERS entry update
   - Documentation typo fixes"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/Documentation: Fix various typos in Documentation/x86/ files
  x86/amd_nb: Fix boot crash on non-AMD systems
  MAINTAINERS: Update the Calgary IOMMU entry

Pull scheduler fixes from Ingo Molnar:
 "Two load-balancing fixes for cgroups-intense workloads"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Fix calc_cfs_shares() fixed point arithmetics width confusion
  sched/fair: Fix effective_load() to consistently use smoothed load

Pull perf fixes from Ingo Molnar:
 "Various fixes:

   - 32-bit callgraph bug fix
   - suboptimal event group scheduling bug fix
   - event constraint fixes for Broadwell/Skylake
   - RAPL module name collision fix"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/core: Fix pmu::filter_match for SW-led groups
  x86/perf/intel/rapl: Fix module name collision with powercap intel-rapl
  perf/x86: Fix 32-bit perf user callgraph collection
  perf/x86/intel: Update event constraints when HT is off

Pull irq fixes from Ingo Molnar:
 "Two MIPS-GIC irqchip driver fixes to unbreak certain MIPS boards"

* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  irqchip/mips-gic: Match IPI IRQ domain by bus token only
  irqchip/mips-gic: Map to VPs using HW VPNum

Pull GPIO fixes from Linus Walleij:
 "I don't like to toss in last minute patches, but these are all for
  things that are broken, and have bitten people for real.  Two of them
  go into stable.  Maybe all of them if the compile test problem is a
  pain in the ass also for stable folks.

  Final (hopefully) GPIO fixes for v4.7:

   - Fix an oops on the Asus Eee PC 1201

   - Revert a patch trying to split GPIO parsing and GPIO configuration

   - Revert a too liberal compile testing thing"

* tag 'gpio-v4.7-5' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio:
  Revert "gpio: gpiolib-of: Allow compile testing"
  Revert "gpiolib: Split GPIO flags parsing and GPIO configuration"
  gpio: sch: Fix Oops on module load on Asus Eee PC 1201

Pull drm fixes from Dave Airlie:
 "One nouveau fix, and a few AMD Polaris fixes and some Allwinner fixes.

  I've got some vmware fixes that I might send separate over the
  weekend, they fix some black screens, but I'm still debating them"

* tag 'drm-fixes-for-v4.7-rc7' of git://people.freedesktop.org/~airlied/linux:
  drm/amd/powerplay: Update CKS on/ CKS off voltage offset calculation.
  drm/amd/powerplay: fix bug that get wrong polaris evv voltage.
  drm/amd/powerplay: incorrectly use of the function return value
  drm/amd/powerplay: fix incorrect voltage table value for tonga
  drm/amd/powerplay: fix incorrect voltage table value for polaris10
  drm/nouveau/disp/sor/gf119: select correct sor when poking training pattern
  gpu: drm: sun4i_drv: add missing of_node_put after calling of_parse_phandle
  drm/sun4i: Send vblank event when the CRTC is disabled
  drm/sun4i: Report proper vblank

There are legitimate reasons to disallow mmap on certain files, notably
in sysfs or procfs.  We shouldn't emulate mmap support on file systems
that don't offer support natively.

CVE-2016-1583
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Cc: stable@vger.kernel.org
[tyhicks: clean up f_op check by using ecryptfs_file_to_lower()]
Signed-off-by: Tyler Hicks <tyhicks@canonical.com>

As of Xen 4.7 PV CPUID doesn't expose either of CPUID[1].ECX[7] and
CPUID[0x80000007].EDX[7] anymore, causing the driver to fail to load on
both Intel and AMD systems. Doing any kind of hardware capability
checks in the driver as a prerequisite was wrong anyway: With the
hypervisor being in charge, all such checking should be done by it. If
ACPI data gets uploaded despite some missing capability, the hypervisor
is free to ignore part or all of that data.

Ditch the entire check_prereq() function, and do the only valid check
(xen_initial_domain()) in the caller in its place.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

No need to retain a local copy of the full request message, only the
type is really needed.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

xenbus_dev_request_and_reply() needs to track whether a transaction is
open.  For XS_TRANSACTION_START messages it calls transaction_start()
and for XS_TRANSACTION_END messages it calls transaction_end().

If sending an XS_TRANSACTION_START message fails or responds with an
an error, the transaction is not open and transaction_end() must be
called.

If sending an XS_TRANSACTION_END message fails, the transaction is
still open, but if an error response is returned the transaction is
closed.

Commit 027bd7e8 ("xen/xenbus: Avoid synchronous wait on XenBus
stalling shutdown/restart") introduced a regression where failed
XS_TRANSACTION_START messages were leaving the transaction open.  This
can cause problems with suspend (and migration) as all transactions
must be closed before suspending.

It appears that the problematic change was added accidentally, so just
remove it.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

Pull apparmor fix from James Morris.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security:
  apparmor: fix oops, validate buffer size in apparmor_setprocattr()

Pull ACPI fixes from Rafael Wysocki:
 "All of these fix recent regressions in ACPICA, in the ACPI PCI IRQ
  management code and in the ACPI AML debugger.

  Specifics:

   - Fix a lock ordering issue in ACPICA introduced by a recent commit
     that attempted to fix a deadlock in the dynamic table loading code
     which in turn appeared after changes related to the handling of
     module-level AML also made in this cycle (Lv Zheng).

   - Fix a recent regression in the ACPI IRQ management code that may
     cause PCI drivers to be unable to register an IRQ if that IRQ
     happens to be shared with a device on the ISA bus, like the
     parallel port, by reverting one commit entirely and restoring the
     previous behavior in two other places (Sinan Kaya).

   - Fix a recent regression in the ACPI AML debugger introduced by the
     commit that removed incorrect usage of IS_ERR_VALUE() from multiple
     places (Lv Zheng)"

* tag 'acpi-4.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  ACPI / debugger: Fix regression introduced by IS_ERR_VALUE() removal
  ACPICA: Namespace: Fix namespace/interpreter lock ordering
  ACPI,PCI,IRQ: separate ISA penalty calculation
  Revert "ACPI, PCI, IRQ: remove redundant code in acpi_irq_penalty_init()"
  ACPI,PCI,IRQ: factor in PCI possible

Pull power management fixes from Rafael Wysocki:
 "One fix for a recent cpuidle core change that, against all odds,
  introduced a functional regression on Power systems and the fix for
  the crash during resume from hibernation on x86-64 that has been in
  the works for the last few weeks (it actually was ready last week, but
  I wanted to allow the reporters to test if for some more time).

  Specifics:

   - Fix a recent performance regression on Power systems (powernv and
     pseries) introduced by a core cpuidle commit that decreased the
     precision of the last_residency conversion from nano- to
     microseconds, which should not matter in theory, but turned out to
     play not-so-well with the special "snooze" idle state on Power
     (Shreyas B Prabhu).

   - Fix a crash during resume from hibernation on x86-64 caused by
     possible corruption of the kernel text part of page tables in the
     last phase of image restoration exposed by a security-related
     change during the 4.3 development cycle (Rafael Wysocki)"

* tag 'pm-4.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpuidle: Fix last_residency division
  x86/power/64: Fix kernel text mapping corruption during image restoration

Merge tag 'sunxi-drm-fixes-for-4.7-2' of https://git.kernel.org/pub/scm/linux/kernel/git/mripard/linux into drm-fixes

Allwinner DRM driver fixes for 4.7, take 2

A new set of fixes for the sun4i driver, mostly related to vblank handling,
and a minor fix to release a reference on the device tree nodes we're
parsing in the probe logic.

* tag 'sunxi-drm-fixes-for-4.7-2' of https://git.kernel.org/pub/scm/linux/kernel/git/mripard/linux:
  gpu: drm: sun4i_drv: add missing of_node_put after calling of_parse_phandle
  drm/sun4i: Send vblank event when the CRTC is disabled
  drm/sun4i: Report proper vblank

When proc_pid_attr_write() was changed to use memdup_user apparmor's
(interface violating) assumption that the setprocattr buffer was always
a single page was violated.

The size test is not strictly speaking needed as proc_pid_attr_write()
will reject anything larger, but for the sake of robustness we can keep
it in.

SMACK and SELinux look safe to me, but somebody else should probably
have a look just in case.

Based on original patch from Vegard Nossum <vegard.nossum@oracle.com>
modified for the case that apparmor provides null termination.

Fixes: bb646cdbReported-by: Vegard Nossum <vegard.nossum@oracle.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: John Johansen <john.johansen@canonical.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Cc: Eric Paris <eparis@parisplace.org>
Cc: Casey Schaufler <casey@schaufler-ca.com>
Cc: stable@kernel.org
Signed-off-by: John Johansen <john.johansen@canonical.com>
Reviewed-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>

This reverts commit 2f36db71.

It fixed a local root exploit but also introduced a dependency on
the lower file system implementing an mmap operation just to open a file,
which is a bit of a heavy hammer.  The right fix is to have mmap depend
on the existence of the mmap handler instead.
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Cc: stable@vger.kernel.org
Signed-off-by: Tyler Hicks <tyhicks@canonical.com>

Pull block IO fixes from Jens Axboe:
 "Three small fixes that have been queued up and tested for this series:

   - A bug fix for xen-blkfront from Bob Liu, fixing an issue with
     incomplete requests during migration.

   - A fix for an ancient issue in retrieving the IO priority of a
     different PID than self, preventing that task from going away while
     we access it.  From Omar.

   - A writeback fix from Tahsin, fixing a case where we'd call ihold()
     with a zero ref count inode"

* 'for-linus' of git://git.kernel.dk/linux-block:
  block: fix use-after-free in sys_ioprio_get()
  writeback: inode cgroup wb switch should not call ihold()
  xen-blkfront: save uncompleted reqs in blkfront_resume()

Pull configfs fix from Christoph Hellwig:
 "A fix from Marek for ppos handling in configfs_write_bin_file, which
  was introduced in Linux 4.5, but didn't have any users until recently"

* tag 'configfs-for-4.7' of git://git.infradead.org/users/hch/configfs:
  configfs: Remove ppos increment in configfs_write_bin_file

* acpica-fixes:
  ACPICA: Namespace: Fix namespace/interpreter lock ordering

* acpi-pci-fixes:
  ACPI,PCI,IRQ: separate ISA penalty calculation
  Revert "ACPI, PCI, IRQ: remove redundant code in acpi_irq_penalty_init()"
  ACPI,PCI,IRQ: factor in PCI possible

* acpi-debug-fixes:
  ACPI / debugger: Fix regression introduced by IS_ERR_VALUE() removal

* pm-cpuidle-fixes:
  cpuidle: Fix last_residency division

* pm-sleep-fixes:
  x86/power/64: Fix kernel text mapping corruption during image restoration